Merge branch 'perf/urgent' into perf/core

Merge reason: queue up dependent patch, update to -rc4

Signed-off-by: Ingo Molnar <mingo@elte.hu>

19 files changed, 1303 insertions, 131 deletions

diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index eecd2a9f155c..9326af5186fe 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -2,14 +2,17 @@
 # Makefile for the Linux/MIPS kernel.
 #
 
-CPPFLAGS_vmlinux.lds := $(KBUILD_CFLAGS)
-
 extra-y		:= head.o init_task.o vmlinux.lds
 
 obj-y		+= cpu-probe.o branch.o entry.o genex.o irq.o process.o \
 		   ptrace.o reset.o setup.o signal.o syscall.o \
 		   time.o topology.o traps.o unaligned.o watch.o
 
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_early_printk.o = -pg
+endif
+
 obj-$(CONFIG_CEVT_BCM1480)	+= cevt-bcm1480.o
 obj-$(CONFIG_CEVT_R4K_LIB)	+= cevt-r4k.o
 obj-$(CONFIG_MIPS_MT_SMTC)	+= cevt-smtc.o
@@ -19,6 +22,7 @@ obj-$(CONFIG_CEVT_SB1250)	+= cevt-sb1250.o
 obj-$(CONFIG_CEVT_TXX9)		+= cevt-txx9.o
 obj-$(CONFIG_CSRC_BCM1480)	+= csrc-bcm1480.o
 obj-$(CONFIG_CSRC_IOASIC)	+= csrc-ioasic.o
+obj-$(CONFIG_CSRC_POWERTV)	+= csrc-powertv.o
 obj-$(CONFIG_CSRC_R4K_LIB)	+= csrc-r4k.o
 obj-$(CONFIG_CSRC_SB1250)	+= csrc-sb1250.o
 obj-$(CONFIG_SYNC_R4K)		+= sync-r4k.o
@@ -26,6 +30,8 @@ obj-$(CONFIG_SYNC_R4K)		+= sync-r4k.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_MODULES)		+= mips_ksyms.o module.o
 
+obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
+
 obj-$(CONFIG_CPU_LOONGSON2)	+= r4k_fpu.o r4k_switch.o
 obj-$(CONFIG_CPU_MIPS32)	+= r4k_fpu.o r4k_switch.o
 obj-$(CONFIG_CPU_MIPS64)	+= r4k_fpu.o r4k_switch.o
@@ -92,4 +98,8 @@ CFLAGS_cpu-bugs64.o	= $(shell if $(CC) $(KBUILD_CFLAGS) -Wa,-mdaddi -c -o /dev/n
 
 obj-$(CONFIG_HAVE_STD_PC_SERIAL_PORT)	+= 8250-platform.o
 
+obj-$(CONFIG_MIPS_CPUFREQ)	+= cpufreq/
+
 EXTRA_CFLAGS += -Werror
+
+CPPFLAGS_vmlinux.lds		:= $(KBUILD_CFLAGS)
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 7a51866068a4..80e202eca056 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -16,6 +16,7 @@
 #include <linux/ptrace.h>
 #include <linux/smp.h>
 #include <linux/stddef.h>
+#include <linux/module.h>
 
 #include <asm/bugs.h>
 #include <asm/cpu.h>
@@ -32,6 +33,7 @@
  * the CPU very much.
  */
 void (*cpu_wait)(void);
+EXPORT_SYMBOL(cpu_wait);
 
 static void r3081_wait(void)
 {
diff --git a/arch/mips/kernel/cpufreq/Kconfig b/arch/mips/kernel/cpufreq/Kconfig
new file mode 100644
index 000000000000..58c601eee6fd
--- /dev/null
+++ b/arch/mips/kernel/cpufreq/Kconfig
@@ -0,0 +1,41 @@
+#
+# CPU Frequency scaling
+#
+
+config MIPS_EXTERNAL_TIMER
+	bool
+
+config MIPS_CPUFREQ
+	bool
+	default y
+	depends on CPU_SUPPORTS_CPUFREQ && MIPS_EXTERNAL_TIMER
+
+if MIPS_CPUFREQ
+
+menu "CPU Frequency scaling"
+
+source "drivers/cpufreq/Kconfig"
+
+if CPU_FREQ
+
+comment "CPUFreq processor drivers"
+
+config LOONGSON2_CPUFREQ
+	tristate "Loongson2 CPUFreq Driver"
+	select CPU_FREQ_TABLE
+	depends on MIPS_CPUFREQ
+	help
+	  This option adds a CPUFreq driver for loongson processors which
+	  support software configurable cpu frequency.
+
+	  Loongson2F and it's successors support this feature.
+
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+
+	  If in doubt, say N.
+
+endif	# CPU_FREQ
+
+endmenu
+
+endif	# MIPS_CPUFREQ
diff --git a/arch/mips/kernel/cpufreq/Makefile b/arch/mips/kernel/cpufreq/Makefile
new file mode 100644
index 000000000000..c3479a432efe
--- /dev/null
+++ b/arch/mips/kernel/cpufreq/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the Linux/MIPS cpufreq.
+#
+
+obj-$(CONFIG_LOONGSON2_CPUFREQ) += loongson2_cpufreq.o loongson2_clock.o
diff --git a/arch/mips/kernel/cpufreq/loongson2_clock.c b/arch/mips/kernel/cpufreq/loongson2_clock.c
new file mode 100644
index 000000000000..d7ca256e33ef
--- /dev/null
+++ b/arch/mips/kernel/cpufreq/loongson2_clock.c
@@ -0,0 +1,166 @@
+/*
+ * Copyright (C) 2006 - 2008 Lemote Inc. & Insititute of Computing Technology
+ * Author: Yanhua, yanh@lemote.com
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/cpufreq.h>
+#include <linux/platform_device.h>
+
+#include <asm/clock.h>
+
+#include <loongson.h>
+
+static LIST_HEAD(clock_list);
+static DEFINE_SPINLOCK(clock_lock);
+static DEFINE_MUTEX(clock_list_sem);
+
+/* Minimum CLK support */
+enum {
+	DC_ZERO, DC_25PT = 2, DC_37PT, DC_50PT, DC_62PT, DC_75PT,
+	DC_87PT, DC_DISABLE, DC_RESV
+};
+
+struct cpufreq_frequency_table loongson2_clockmod_table[] = {
+	{DC_RESV, CPUFREQ_ENTRY_INVALID},
+	{DC_ZERO, CPUFREQ_ENTRY_INVALID},
+	{DC_25PT, 0},
+	{DC_37PT, 0},
+	{DC_50PT, 0},
+	{DC_62PT, 0},
+	{DC_75PT, 0},
+	{DC_87PT, 0},
+	{DC_DISABLE, 0},
+	{DC_RESV, CPUFREQ_TABLE_END},
+};
+EXPORT_SYMBOL_GPL(loongson2_clockmod_table);
+
+static struct clk cpu_clk = {
+	.name = "cpu_clk",
+	.flags = CLK_ALWAYS_ENABLED | CLK_RATE_PROPAGATES,
+	.rate = 800000000,
+};
+
+struct clk *clk_get(struct device *dev, const char *id)
+{
+	return &cpu_clk;
+}
+EXPORT_SYMBOL(clk_get);
+
+static void propagate_rate(struct clk *clk)
+{
+	struct clk *clkp;
+
+	list_for_each_entry(clkp, &clock_list, node) {
+		if (likely(clkp->parent != clk))
+			continue;
+		if (likely(clkp->ops && clkp->ops->recalc))
+			clkp->ops->recalc(clkp);
+		if (unlikely(clkp->flags & CLK_RATE_PROPAGATES))
+			propagate_rate(clkp);
+	}
+}
+
+int clk_enable(struct clk *clk)
+{
+	return 0;
+}
+EXPORT_SYMBOL(clk_enable);
+
+void clk_disable(struct clk *clk)
+{
+}
+EXPORT_SYMBOL(clk_disable);
+
+unsigned long clk_get_rate(struct clk *clk)
+{
+	return (unsigned long)clk->rate;
+}
+EXPORT_SYMBOL(clk_get_rate);
+
+void clk_put(struct clk *clk)
+{
+}
+EXPORT_SYMBOL(clk_put);
+
+int clk_set_rate(struct clk *clk, unsigned long rate)
+{
+	return clk_set_rate_ex(clk, rate, 0);
+}
+EXPORT_SYMBOL_GPL(clk_set_rate);
+
+int clk_set_rate_ex(struct clk *clk, unsigned long rate, int algo_id)
+{
+	int ret = 0;
+	int regval;
+	int i;
+
+	if (likely(clk->ops && clk->ops->set_rate)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&clock_lock, flags);
+		ret = clk->ops->set_rate(clk, rate, algo_id);
+		spin_unlock_irqrestore(&clock_lock, flags);
+	}
+
+	if (unlikely(clk->flags & CLK_RATE_PROPAGATES))
+		propagate_rate(clk);
+
+	for (i = 0; loongson2_clockmod_table[i].frequency != CPUFREQ_TABLE_END;
+	     i++) {
+		if (loongson2_clockmod_table[i].frequency ==
+		    CPUFREQ_ENTRY_INVALID)
+			continue;
+		if (rate == loongson2_clockmod_table[i].frequency)
+			break;
+	}
+	if (rate != loongson2_clockmod_table[i].frequency)
+		return -ENOTSUPP;
+
+	clk->rate = rate;
+
+	regval = LOONGSON_CHIPCFG0;
+	regval = (regval & ~0x7) | (loongson2_clockmod_table[i].index - 1);
+	LOONGSON_CHIPCFG0 = regval;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clk_set_rate_ex);
+
+long clk_round_rate(struct clk *clk, unsigned long rate)
+{
+	if (likely(clk->ops && clk->ops->round_rate)) {
+		unsigned long flags, rounded;
+
+		spin_lock_irqsave(&clock_lock, flags);
+		rounded = clk->ops->round_rate(clk, rate);
+		spin_unlock_irqrestore(&clock_lock, flags);
+
+		return rounded;
+	}
+
+	return rate;
+}
+EXPORT_SYMBOL_GPL(clk_round_rate);
+
+/*
+ * This is the simple version of Loongson-2 wait, Maybe we need do this in
+ * interrupt disabled content
+ */
+
+DEFINE_SPINLOCK(loongson2_wait_lock);
+void loongson2_cpu_wait(void)
+{
+	u32 cpu_freq;
+	unsigned long flags;
+
+	spin_lock_irqsave(&loongson2_wait_lock, flags);
+	cpu_freq = LOONGSON_CHIPCFG0;
+	LOONGSON_CHIPCFG0 &= ~0x7;	/* Put CPU into wait mode */
+	LOONGSON_CHIPCFG0 = cpu_freq;	/* Restore CPU state */
+	spin_unlock_irqrestore(&loongson2_wait_lock, flags);
+}
+EXPORT_SYMBOL_GPL(loongson2_cpu_wait);
diff --git a/arch/mips/kernel/cpufreq/loongson2_cpufreq.c b/arch/mips/kernel/cpufreq/loongson2_cpufreq.c
new file mode 100644
index 000000000000..2f6a0b147ab8
--- /dev/null
+++ b/arch/mips/kernel/cpufreq/loongson2_cpufreq.c
@@ -0,0 +1,227 @@
+/*
+ * Cpufreq driver for the loongson-2 processors
+ *
+ * The 2E revision of loongson processor not support this feature.
+ *
+ * Copyright (C) 2006 - 2008 Lemote Inc. & Insititute of Computing Technology
+ * Author: Yanhua, yanh@lemote.com
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/cpufreq.h>
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/sched.h>	/* set_cpus_allowed() */
+#include <linux/delay.h>
+#include <linux/platform_device.h>
+
+#include <asm/clock.h>
+
+#include <loongson.h>
+
+static uint nowait;
+
+static struct clk *cpuclk;
+
+static void (*saved_cpu_wait) (void);
+
+static int loongson2_cpu_freq_notifier(struct notifier_block *nb,
+					unsigned long val, void *data);
+
+static struct notifier_block loongson2_cpufreq_notifier_block = {
+	.notifier_call = loongson2_cpu_freq_notifier
+};
+
+static int loongson2_cpu_freq_notifier(struct notifier_block *nb,
+					unsigned long val, void *data)
+{
+	if (val == CPUFREQ_POSTCHANGE)
+		current_cpu_data.udelay_val = loops_per_jiffy;
+
+	return 0;
+}
+
+static unsigned int loongson2_cpufreq_get(unsigned int cpu)
+{
+	return clk_get_rate(cpuclk);
+}
+
+/*
+ * Here we notify other drivers of the proposed change and the final change.
+ */
+static int loongson2_cpufreq_target(struct cpufreq_policy *policy,
+				     unsigned int target_freq,
+				     unsigned int relation)
+{
+	unsigned int cpu = policy->cpu;
+	unsigned int newstate = 0;
+	cpumask_t cpus_allowed;
+	struct cpufreq_freqs freqs;
+	unsigned int freq;
+
+	if (!cpu_online(cpu))
+		return -ENODEV;
+
+	cpus_allowed = current->cpus_allowed;
+	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+
+	if (cpufreq_frequency_table_target
+	    (policy, &loongson2_clockmod_table[0], target_freq, relation,
+	     &newstate))
+		return -EINVAL;
+
+	freq =
+	    ((cpu_clock_freq / 1000) *
+	     loongson2_clockmod_table[newstate].index) / 8;
+	if (freq < policy->min || freq > policy->max)
+		return -EINVAL;
+
+	pr_debug("cpufreq: requested frequency %u Hz\n", target_freq * 1000);
+
+	freqs.cpu = cpu;
+	freqs.old = loongson2_cpufreq_get(cpu);
+	freqs.new = freq;
+	freqs.flags = 0;
+
+	if (freqs.new == freqs.old)
+		return 0;
+
+	/* notifiers */
+	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+
+	set_cpus_allowed(current, cpus_allowed);
+
+	/* setting the cpu frequency */
+	clk_set_rate(cpuclk, freq);
+
+	/* notifiers */
+	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+
+	pr_debug("cpufreq: set frequency %u kHz\n", freq);
+
+	return 0;
+}
+
+static int loongson2_cpufreq_cpu_init(struct cpufreq_policy *policy)
+{
+	int i;
+
+	if (!cpu_online(policy->cpu))
+		return -ENODEV;
+
+	cpuclk = clk_get(NULL, "cpu_clk");
+	if (IS_ERR(cpuclk)) {
+		printk(KERN_ERR "cpufreq: couldn't get CPU clk\n");
+		return PTR_ERR(cpuclk);
+	}
+
+	cpuclk->rate = cpu_clock_freq / 1000;
+	if (!cpuclk->rate)
+		return -EINVAL;
+
+	/* clock table init */
+	for (i = 2;
+	     (loongson2_clockmod_table[i].frequency != CPUFREQ_TABLE_END);
+	     i++)
+		loongson2_clockmod_table[i].frequency = (cpuclk->rate * i) / 8;
+
+	policy->cur = loongson2_cpufreq_get(policy->cpu);
+
+	cpufreq_frequency_table_get_attr(&loongson2_clockmod_table[0],
+					 policy->cpu);
+
+	return cpufreq_frequency_table_cpuinfo(policy,
+					    &loongson2_clockmod_table[0]);
+}
+
+static int loongson2_cpufreq_verify(struct cpufreq_policy *policy)
+{
+	return cpufreq_frequency_table_verify(policy,
+					      &loongson2_clockmod_table[0]);
+}
+
+static int loongson2_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	clk_put(cpuclk);
+	return 0;
+}
+
+static struct freq_attr *loongson2_table_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,
+};
+
+static struct cpufreq_driver loongson2_cpufreq_driver = {
+	.owner = THIS_MODULE,
+	.name = "loongson2",
+	.init = loongson2_cpufreq_cpu_init,
+	.verify = loongson2_cpufreq_verify,
+	.target = loongson2_cpufreq_target,
+	.get = loongson2_cpufreq_get,
+	.exit = loongson2_cpufreq_exit,
+	.attr = loongson2_table_attr,
+};
+
+static struct platform_device_id platform_device_ids[] = {
+	{
+		.name = "loongson2_cpufreq",
+	},
+	{}
+};
+
+MODULE_DEVICE_TABLE(platform, platform_device_ids);
+
+static struct platform_driver platform_driver = {
+	.driver = {
+		.name = "loongson2_cpufreq",
+		.owner = THIS_MODULE,
+	},
+	.id_table = platform_device_ids,
+};
+
+static int __init cpufreq_init(void)
+{
+	int ret;
+
+	/* Register platform stuff */
+	ret = platform_driver_register(&platform_driver);
+	if (ret)
+		return ret;
+
+	pr_info("cpufreq: Loongson-2F CPU frequency driver.\n");
+
+	cpufreq_register_notifier(&loongson2_cpufreq_notifier_block,
+				  CPUFREQ_TRANSITION_NOTIFIER);
+
+	ret = cpufreq_register_driver(&loongson2_cpufreq_driver);
+
+	if (!ret && !nowait) {
+		saved_cpu_wait = cpu_wait;
+		cpu_wait = loongson2_cpu_wait;
+	}
+
+	return ret;
+}
+
+static void __exit cpufreq_exit(void)
+{
+	if (!nowait && saved_cpu_wait)
+		cpu_wait = saved_cpu_wait;
+	cpufreq_unregister_driver(&loongson2_cpufreq_driver);
+	cpufreq_unregister_notifier(&loongson2_cpufreq_notifier_block,
+				    CPUFREQ_TRANSITION_NOTIFIER);
+
+	platform_driver_unregister(&platform_driver);
+}
+
+module_init(cpufreq_init);
+module_exit(cpufreq_exit);
+
+module_param(nowait, uint, 0644);
+MODULE_PARM_DESC(nowait, "Disable Loongson-2F specific wait");
+
+MODULE_AUTHOR("Yanhua <yanh@lemote.com>");
+MODULE_DESCRIPTION("cpufreq driver for Loongson2F");
+MODULE_LICENSE("GPL");
diff --git a/arch/mips/kernel/csrc-powertv.c b/arch/mips/kernel/csrc-powertv.c
new file mode 100644
index 000000000000..a27c16c8690e
--- /dev/null
+++ b/arch/mips/kernel/csrc-powertv.c
@@ -0,0 +1,180 @@
+/*
+ * Copyright (C) 2008 Scientific-Atlanta, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+ */
+/*
+ * The file comes from kernel/csrc-r4k.c
+ */
+#include <linux/clocksource.h>
+#include <linux/init.h>
+
+#include <asm/time.h>			/* Not included in linux/time.h */
+
+#include <asm/mach-powertv/asic_regs.h>
+#include "powertv-clock.h"
+
+/* MIPS PLL Register Definitions */
+#define PLL_GET_M(x)		(((x) >> 8) & 0x000000FF)
+#define PLL_GET_N(x)		(((x) >> 16) & 0x000000FF)
+#define PLL_GET_P(x)		(((x) >> 24) & 0x00000007)
+
+/*
+ * returns:  Clock frequency in kHz
+ */
+unsigned int __init mips_get_pll_freq(void)
+{
+	unsigned int pll_reg, m, n, p;
+	unsigned int fin = 54000; /* Base frequency in kHz */
+	unsigned int fout;
+
+	/* Read PLL register setting */
+	pll_reg = asic_read(mips_pll_setup);
+	m = PLL_GET_M(pll_reg);
+	n = PLL_GET_N(pll_reg);
+	p = PLL_GET_P(pll_reg);
+	pr_info("MIPS PLL Register:0x%x  M=%d  N=%d  P=%d\n", pll_reg, m, n, p);
+
+	/* Calculate clock frequency = (2 * N * 54MHz) / (M * (2**P)) */
+	fout = ((2 * n * fin) / (m * (0x01 << p)));
+
+	pr_info("MIPS Clock Freq=%d kHz\n", fout);
+
+	return fout;
+}
+
+static cycle_t c0_hpt_read(struct clocksource *cs)
+{
+	return read_c0_count();
+}
+
+static struct clocksource clocksource_mips = {
+	.name		= "powertv-counter",
+	.read		= c0_hpt_read,
+	.mask		= CLOCKSOURCE_MASK(32),
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static void __init powertv_c0_hpt_clocksource_init(void)
+{
+	unsigned int pll_freq = mips_get_pll_freq();
+
+	pr_info("CPU frequency %d.%02d MHz\n", pll_freq / 1000,
+		(pll_freq % 1000) * 100 / 1000);
+
+	mips_hpt_frequency = pll_freq / 2 * 1000;
+
+	clocksource_mips.rating = 200 + mips_hpt_frequency / 10000000;
+
+	clocksource_set_clock(&clocksource_mips, mips_hpt_frequency);
+
+	clocksource_register(&clocksource_mips);
+}
+
+/**
+ * struct tim_c - free running counter
+ * @hi:	High 16 bits of the counter
+ * @lo:	Low 32 bits of the counter
+ *
+ * Lays out the structure of the free running counter in memory. This counter
+ * increments at a rate of 27 MHz/8 on all platforms.
+ */
+struct tim_c {
+	unsigned int hi;
+	unsigned int lo;
+};
+
+static struct tim_c *tim_c;
+
+static cycle_t tim_c_read(struct clocksource *cs)
+{
+	unsigned int hi;
+	unsigned int next_hi;
+	unsigned int lo;
+
+	hi = readl(&tim_c->hi);
+
+	for (;;) {
+		lo = readl(&tim_c->lo);
+		next_hi = readl(&tim_c->hi);
+		if (next_hi == hi)
+			break;
+		hi = next_hi;
+	}
+
+pr_crit("%s: read %llx\n", __func__, ((u64) hi << 32) | lo);
+	return ((u64) hi << 32) | lo;
+}
+
+#define TIM_C_SIZE		48		/* # bits in the timer */
+
+static struct clocksource clocksource_tim_c = {
+	.name		= "powertv-tim_c",
+	.read		= tim_c_read,
+	.mask		= CLOCKSOURCE_MASK(TIM_C_SIZE),
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+/**
+ * powertv_tim_c_clocksource_init - set up a clock source for the TIM_C clock
+ *
+ * The hard part here is coming up with a constant k and shift s such that
+ * the 48-bit TIM_C value multiplied by k doesn't overflow and that value,
+ * when shifted right by s, yields the corresponding number of nanoseconds.
+ * We know that TIM_C counts at 27 MHz/8, so each cycle corresponds to
+ * 1 / (27,000,000/8) seconds. Multiply that by a billion and you get the
+ * number of nanoseconds. Since the TIM_C value has 48 bits and the math is
+ * done in 64 bits, avoiding an overflow means that k must be less than
+ * 64 - 48 = 16 bits.
+ */
+static void __init powertv_tim_c_clocksource_init(void)
+{
+	int			prescale;
+	unsigned long		dividend;
+	unsigned long		k;
+	int			s;
+	const int		max_k_bits = (64 - 48) - 1;
+	const unsigned long	billion = 1000000000;
+	const unsigned long	counts_per_second = 27000000 / 8;
+
+	prescale = BITS_PER_LONG - ilog2(billion) - 1;
+	dividend = billion << prescale;
+	k = dividend / counts_per_second;
+	s = ilog2(k) - max_k_bits;
+
+	if (s < 0)
+		s = prescale;
+
+	else {
+		k >>= s;
+		s += prescale;
+	}
+
+	clocksource_tim_c.mult = k;
+	clocksource_tim_c.shift = s;
+	clocksource_tim_c.rating = 200;
+
+	clocksource_register(&clocksource_tim_c);
+	tim_c = (struct tim_c *) asic_reg_addr(tim_ch);
+}
+
+/**
+ powertv_clocksource_init - initialize all clocksources
+ */
+void __init powertv_clocksource_init(void)
+{
+	powertv_c0_hpt_clocksource_init();
+	powertv_tim_c_clocksource_init();
+}
diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
new file mode 100644
index 000000000000..68b067040d8b
--- /dev/null
+++ b/arch/mips/kernel/ftrace.c
@@ -0,0 +1,275 @@
+/*
+ * Code for replacing ftrace calls with jumps.
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2009 DSLab, Lanzhou University, China
+ * Author: Wu Zhangjin <wuzj@lemote.com>
+ *
+ * Thanks goes to Steven Rostedt for writing the original x86 version.
+ */
+
+#include <linux/uaccess.h>
+#include <linux/init.h>
+#include <linux/ftrace.h>
+
+#include <asm/cacheflush.h>
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+#define JAL 0x0c000000		/* jump & link: ip --> ra, jump to target */
+#define ADDR_MASK 0x03ffffff	/*  op_code|addr : 31...26|25 ....0 */
+#define jump_insn_encode(op_code, addr) \
+	((unsigned int)((op_code) | (((addr) >> 2) & ADDR_MASK)))
+
+static unsigned int ftrace_nop = 0x00000000;
+
+static int ftrace_modify_code(unsigned long ip, unsigned int new_code)
+{
+	int faulted;
+
+	/* *(unsigned int *)ip = new_code; */
+	safe_store_code(new_code, ip, faulted);
+
+	if (unlikely(faulted))
+		return -EFAULT;
+
+	flush_icache_range(ip, ip + 8);
+
+	return 0;
+}
+
+static int lui_v1;
+static int jal_mcount;
+
+int ftrace_make_nop(struct module *mod,
+		    struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned int new;
+	int faulted;
+	unsigned long ip = rec->ip;
+
+	/* We have compiled module with -mlong-calls, but compiled the kernel
+	 * without it, we need to cope with them respectively. */
+	if (ip & 0x40000000) {
+		/* record it for ftrace_make_call */
+		if (lui_v1 == 0) {
+			/* lui_v1 = *(unsigned int *)ip; */
+			safe_load_code(lui_v1, ip, faulted);
+
+			if (unlikely(faulted))
+				return -EFAULT;
+		}
+
+		/* lui v1, hi_16bit_of_mcount        --> b 1f (0x10000004)
+		 * addiu v1, v1, low_16bit_of_mcount
+		 * move at, ra
+		 * jalr v1
+		 * nop
+		 * 				     1f: (ip + 12)
+		 */
+		new = 0x10000004;
+	} else {
+		/* record/calculate it for ftrace_make_call */
+		if (jal_mcount == 0) {
+			/* We can record it directly like this:
+			 *     jal_mcount = *(unsigned int *)ip;
+			 * Herein, jump over the first two nop instructions */
+			jal_mcount = jump_insn_encode(JAL, (MCOUNT_ADDR + 8));
+		}
+
+		/* move at, ra
+		 * jalr v1		--> nop
+		 */
+		new = ftrace_nop;
+	}
+	return ftrace_modify_code(ip, new);
+}
+
+static int modified;	/* initialized as 0 by default */
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned int new;
+	unsigned long ip = rec->ip;
+
+	/* We just need to remove the "b ftrace_stub" at the fist time! */
+	if (modified == 0) {
+		modified = 1;
+		ftrace_modify_code(addr, ftrace_nop);
+	}
+	/* ip, module: 0xc0000000, kernel: 0x80000000 */
+	new = (ip & 0x40000000) ? lui_v1 : jal_mcount;
+
+	return ftrace_modify_code(ip, new);
+}
+
+#define FTRACE_CALL_IP ((unsigned long)(&ftrace_call))
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned int new;
+
+	new = jump_insn_encode(JAL, (unsigned long)func);
+
+	return ftrace_modify_code(FTRACE_CALL_IP, new);
+}
+
+int __init ftrace_dyn_arch_init(void *data)
+{
+	/* The return code is retured via data */
+	*(unsigned long *)data = 0;
+
+	return 0;
+}
+#endif				/* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+extern void ftrace_graph_call(void);
+#define JMP	0x08000000	/* jump to target directly */
+#define CALL_FTRACE_GRAPH_CALLER \
+	jump_insn_encode(JMP, (unsigned long)(&ftrace_graph_caller))
+#define FTRACE_GRAPH_CALL_IP	((unsigned long)(&ftrace_graph_call))
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_code(FTRACE_GRAPH_CALL_IP,
+				  CALL_FTRACE_GRAPH_CALLER);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_code(FTRACE_GRAPH_CALL_IP, ftrace_nop);
+}
+
+#endif				/* !CONFIG_DYNAMIC_FTRACE */
+
+#ifndef KBUILD_MCOUNT_RA_ADDRESS
+#define S_RA_SP	(0xafbf << 16)	/* s{d,w} ra, offset(sp) */
+#define S_R_SP	(0xafb0 << 16)  /* s{d,w} R, offset(sp) */
+#define OFFSET_MASK	0xffff	/* stack offset range: 0 ~ PT_SIZE */
+
+unsigned long ftrace_get_parent_addr(unsigned long self_addr,
+				     unsigned long parent,
+				     unsigned long parent_addr,
+				     unsigned long fp)
+{
+	unsigned long sp, ip, ra;
+	unsigned int code;
+	int faulted;
+
+	/* in module or kernel? */
+	if (self_addr & 0x40000000) {
+		/* module: move to the instruction "lui v1, HI_16BIT_OF_MCOUNT" */
+		ip = self_addr - 20;
+	} else {
+		/* kernel: move to the instruction "move ra, at" */
+		ip = self_addr - 12;
+	}
+
+	/* search the text until finding the non-store instruction or "s{d,w}
+	 * ra, offset(sp)" instruction */
+	do {
+		ip -= 4;
+
+		/* get the code at "ip": code = *(unsigned int *)ip; */
+		safe_load_code(code, ip, faulted);
+
+		if (unlikely(faulted))
+			return 0;
+
+		/* If we hit the non-store instruction before finding where the
+		 * ra is stored, then this is a leaf function and it does not
+		 * store the ra on the stack. */
+		if ((code & S_R_SP) != S_R_SP)
+			return parent_addr;
+
+	} while (((code & S_RA_SP) != S_RA_SP));
+
+	sp = fp + (code & OFFSET_MASK);
+
+	/* ra = *(unsigned long *)sp; */
+	safe_load_stack(ra, sp, faulted);
+	if (unlikely(faulted))
+		return 0;
+
+	if (ra == parent)
+		return sp;
+	return 0;
+}
+
+#endif
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long fp)
+{
+	unsigned long old;
+	struct ftrace_graph_ent trace;
+	unsigned long return_hooker = (unsigned long)
+	    &return_to_handler;
+	int faulted;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	/* "parent" is the stack address saved the return address of the caller
+	 * of _mcount.
+	 *
+	 * if the gcc < 4.5, a leaf function does not save the return address
+	 * in the stack address, so, we "emulate" one in _mcount's stack space,
+	 * and hijack it directly, but for a non-leaf function, it save the
+	 * return address to the its own stack space, we can not hijack it
+	 * directly, but need to find the real stack address,
+	 * ftrace_get_parent_addr() does it!
+	 *
+	 * if gcc>= 4.5, with the new -mmcount-ra-address option, for a
+	 * non-leaf function, the location of the return address will be saved
+	 * to $12 for us, and for a leaf function, only put a zero into $12. we
+	 * do it in ftrace_graph_caller of mcount.S.
+	 */
+
+	/* old = *parent; */
+	safe_load_stack(old, parent, faulted);
+	if (unlikely(faulted))
+		goto out;
+#ifndef KBUILD_MCOUNT_RA_ADDRESS
+	parent = (unsigned long *)ftrace_get_parent_addr(self_addr, old,
+							 (unsigned long)parent,
+							 fp);
+	/* If fails when getting the stack address of the non-leaf function's
+	 * ra, stop function graph tracer and return */
+	if (parent == 0)
+		goto out;
+#endif
+	/* *parent = return_hooker; */
+	safe_store_stack(return_hooker, parent, faulted);
+	if (unlikely(faulted))
+		goto out;
+
+	if (ftrace_push_return_trace(old, self_addr, &trace.depth, fp) ==
+	    -EBUSY) {
+		*parent = old;
+		return;
+	}
+
+	trace.func = self_addr;
+
+	/* Only trace if the calling function expects to */
+	if (!ftrace_graph_entry(&trace)) {
+		current->curr_ret_stack--;
+		*parent = old;
+	}
+	return;
+out:
+	ftrace_graph_stop();
+	WARN_ON(1);
+}
+#endif				/* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index 8b0b4181219f..981f86c26168 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -22,6 +22,7 @@
 #include <linux/seq_file.h>
 #include <linux/kallsyms.h>
 #include <linux/kgdb.h>
+#include <linux/ftrace.h>
 
 #include <asm/atomic.h>
 #include <asm/system.h>
@@ -150,3 +151,32 @@ void __init init_IRQ(void)
 		kgdb_early_setup = 1;
 #endif
 }
+
+/*
+ * do_IRQ handles all normal device IRQ's (the special
+ * SMP cross-CPU interrupts have their own specific
+ * handlers).
+ */
+void __irq_entry do_IRQ(unsigned int irq)
+{
+	irq_enter();
+	__DO_IRQ_SMTC_HOOK(irq);
+	generic_handle_irq(irq);
+	irq_exit();
+}
+
+#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF
+/*
+ * To avoid inefficient and in some cases pathological re-checking of
+ * IRQ affinity, we have this variant that skips the affinity check.
+ */
+
+void __irq_entry do_IRQ_no_affinity(unsigned int irq)
+{
+	irq_enter();
+	__NO_AFFINITY_IRQ_SMTC_HOOK(irq);
+	generic_handle_irq(irq);
+	irq_exit();
+}
+
+#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
new file mode 100644
index 000000000000..0a9cfdb271dd
--- /dev/null
+++ b/arch/mips/kernel/mcount.S
@@ -0,0 +1,189 @@
+/*
+ * MIPS specific _mcount support
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive for
+ * more details.
+ *
+ * Copyright (C) 2009 Lemote Inc. & DSLab, Lanzhou University, China
+ * Author: Wu Zhangjin <wuzj@lemote.com>
+ */
+
+#include <asm/regdef.h>
+#include <asm/stackframe.h>
+#include <asm/ftrace.h>
+
+	.text
+	.set noreorder
+	.set noat
+
+	.macro MCOUNT_SAVE_REGS
+	PTR_SUBU	sp, PT_SIZE
+	PTR_S	ra, PT_R31(sp)
+	PTR_S	AT, PT_R1(sp)
+	PTR_S	a0, PT_R4(sp)
+	PTR_S	a1, PT_R5(sp)
+	PTR_S	a2, PT_R6(sp)
+	PTR_S	a3, PT_R7(sp)
+#ifdef CONFIG_64BIT
+	PTR_S	a4, PT_R8(sp)
+	PTR_S	a5, PT_R9(sp)
+	PTR_S	a6, PT_R10(sp)
+	PTR_S	a7, PT_R11(sp)
+#endif
+	.endm
+
+	.macro MCOUNT_RESTORE_REGS
+	PTR_L	ra, PT_R31(sp)
+	PTR_L	AT, PT_R1(sp)
+	PTR_L	a0, PT_R4(sp)
+	PTR_L	a1, PT_R5(sp)
+	PTR_L	a2, PT_R6(sp)
+	PTR_L	a3, PT_R7(sp)
+#ifdef CONFIG_64BIT
+	PTR_L	a4, PT_R8(sp)
+	PTR_L	a5, PT_R9(sp)
+	PTR_L	a6, PT_R10(sp)
+	PTR_L	a7, PT_R11(sp)
+#endif
+#ifdef CONFIG_64BIT
+	PTR_ADDIU	sp, PT_SIZE
+#else
+	PTR_ADDIU	sp, (PT_SIZE + 8)
+#endif
+.endm
+
+	.macro RETURN_BACK
+	jr ra
+	 move ra, AT
+	.endm
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+NESTED(ftrace_caller, PT_SIZE, ra)
+	.globl _mcount
+_mcount:
+	b	ftrace_stub
+	 nop
+	lw	t1, function_trace_stop
+	bnez	t1, ftrace_stub
+	 nop
+
+	MCOUNT_SAVE_REGS
+#ifdef KBUILD_MCOUNT_RA_ADDRESS
+	PTR_S	t0, PT_R12(sp)	/* t0 saved the location of the return address(at) by -mmcount-ra-address */
+#endif
+
+	move	a0, ra		/* arg1: next ip, selfaddr */
+	.globl ftrace_call
+ftrace_call:
+	nop	/* a placeholder for the call to a real tracing function */
+	 move	a1, AT		/* arg2: the caller's next ip, parent */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	.globl ftrace_graph_call
+ftrace_graph_call:
+	nop
+	 nop
+#endif
+
+	MCOUNT_RESTORE_REGS
+	.globl ftrace_stub
+ftrace_stub:
+	RETURN_BACK
+	END(ftrace_caller)
+
+#else	/* ! CONFIG_DYNAMIC_FTRACE */
+
+NESTED(_mcount, PT_SIZE, ra)
+	lw	t1, function_trace_stop
+	bnez	t1, ftrace_stub
+	 nop
+	PTR_LA	t1, ftrace_stub
+	PTR_L	t2, ftrace_trace_function /* Prepare t2 for (1) */
+	bne	t1, t2, static_trace
+	 nop
+
+#ifdef	CONFIG_FUNCTION_GRAPH_TRACER
+	PTR_L	t3, ftrace_graph_return
+	bne	t1, t3, ftrace_graph_caller
+	 nop
+	PTR_LA	t1, ftrace_graph_entry_stub
+	PTR_L	t3, ftrace_graph_entry
+	bne	t1, t3, ftrace_graph_caller
+	 nop
+#endif
+	b	ftrace_stub
+	 nop
+
+static_trace:
+	MCOUNT_SAVE_REGS
+
+	move	a0, ra		/* arg1: next ip, selfaddr */
+	jalr	t2		/* (1) call *ftrace_trace_function */
+	 move	a1, AT		/* arg2: the caller's next ip, parent */
+
+	MCOUNT_RESTORE_REGS
+	.globl ftrace_stub
+ftrace_stub:
+	RETURN_BACK
+	END(_mcount)
+
+#endif	/* ! CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+NESTED(ftrace_graph_caller, PT_SIZE, ra)
+#ifdef CONFIG_DYNAMIC_FTRACE
+	PTR_L	a1, PT_R31(sp)	/* load the original ra from the stack */
+#ifdef KBUILD_MCOUNT_RA_ADDRESS
+	PTR_L	t0, PT_R12(sp)	/* load the original t0 from the stack */
+#endif
+#else
+	MCOUNT_SAVE_REGS
+	move	a1, ra		/* arg2: next ip, selfaddr */
+#endif
+
+#ifdef KBUILD_MCOUNT_RA_ADDRESS
+	bnez	t0, 1f		/* non-leaf func: t0 saved the location of the return address */
+	 nop
+	PTR_LA	t0, PT_R1(sp)	/* leaf func: get the location of at(old ra) from our own stack */
+1:	move	a0, t0		/* arg1: the location of the return address */
+#else
+	PTR_LA	a0, PT_R1(sp)	/* arg1: &AT -> a0 */
+#endif
+	jal	prepare_ftrace_return
+#ifdef CONFIG_FRAME_POINTER
+	 move	a2, fp		/* arg3: frame pointer */
+#else
+#ifdef CONFIG_64BIT
+	 PTR_LA	a2, PT_SIZE(sp)
+#else
+	 PTR_LA	a2, (PT_SIZE+8)(sp)
+#endif
+#endif
+
+	MCOUNT_RESTORE_REGS
+	RETURN_BACK
+	END(ftrace_graph_caller)
+
+	.align	2
+	.globl	return_to_handler
+return_to_handler:
+	PTR_SUBU	sp, PT_SIZE
+	PTR_S	v0, PT_R2(sp)
+
+	jal	ftrace_return_to_handler
+	 PTR_S	v1, PT_R3(sp)
+
+	/* restore the real parent address: v0 -> ra */
+	move	ra, v0
+
+	PTR_L	v0, PT_R2(sp)
+	PTR_L	v1, PT_R3(sp)
+	jr	ra
+	 PTR_ADDIU	sp, PT_SIZE
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+	.set at
+	.set reorder
diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c
index 225755d0c1f6..1d04807874db 100644
--- a/arch/mips/kernel/mips_ksyms.c
+++ b/arch/mips/kernel/mips_ksyms.c
@@ -13,6 +13,7 @@
 #include <asm/checksum.h>
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
+#include <asm/ftrace.h>
 
 extern void *__bzero(void *__s, size_t __count);
 extern long __strncpy_from_user_nocheck_asm(char *__to,
@@ -51,3 +52,7 @@ EXPORT_SYMBOL(csum_partial_copy_nocheck);
 EXPORT_SYMBOL(__csum_partial_copy_user);
 
 EXPORT_SYMBOL(invalid_pte_table);
+#ifdef CONFIG_FUNCTION_TRACER
+/* _mcount is defined in arch/mips/kernel/mcount.S */
+EXPORT_SYMBOL(_mcount);
+#endif
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 2b290d70083e..f9513f9e61d3 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -58,8 +58,12 @@ EXPORT_SYMBOL(mips_machtype);
 
 struct boot_mem_map boot_mem_map;
 
-static char command_line[CL_SIZE];
-       char arcs_cmdline[CL_SIZE]=CONFIG_CMDLINE;
+static char __initdata command_line[COMMAND_LINE_SIZE];
+char __initdata arcs_cmdline[COMMAND_LINE_SIZE];
+
+#ifdef CONFIG_CMDLINE_BOOL
+static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE;
+#endif
 
 /*
  * mips_io_port_base is the begin of the address space to which x86 style
@@ -166,26 +170,8 @@ static unsigned long __init init_initrd(void)
 	 * already set up initrd_start and initrd_end. In these cases
 	 * perfom sanity checks and use them if all looks good.
 	 */
-	if (!initrd_start || initrd_end <= initrd_start) {
-#ifdef CONFIG_PROBE_INITRD_HEADER
-		u32 *initrd_header;
-
-		/*
-		 * See if initrd has been added to the kernel image by
-		 * arch/mips/boot/addinitrd.c. In that case a header is
-		 * prepended to initrd and is made up by 8 bytes. The first
-		 * word is a magic number and the second one is the size of
-		 * initrd.  Initrd start must be page aligned in any cases.
-		 */
-		initrd_header = __va(PAGE_ALIGN(__pa_symbol(&_end) + 8)) - 8;
-		if (initrd_header[0] != 0x494E5244)
-			goto disable;
-		initrd_start = (unsigned long)(initrd_header + 2);
-		initrd_end = initrd_start + initrd_header[1];
-#else
+	if (!initrd_start || initrd_end <= initrd_start)
 		goto disable;
-#endif
-	}
 
 	if (initrd_start & ~PAGE_MASK) {
 		pr_err("initrd start must be page aligned\n");
@@ -476,8 +462,20 @@ static void __init arch_mem_init(char **cmdline_p)
 	pr_info("Determined physical RAM map:\n");
 	print_memory_map();
 
-	strlcpy(command_line, arcs_cmdline, sizeof(command_line));
-	strlcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
+#ifdef CONFIG_CMDLINE_BOOL
+#ifdef CONFIG_CMDLINE_OVERRIDE
+	strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+#else
+	if (builtin_cmdline[0]) {
+		strlcat(arcs_cmdline, " ", COMMAND_LINE_SIZE);
+		strlcat(arcs_cmdline, builtin_cmdline, COMMAND_LINE_SIZE);
+	}
+	strlcpy(boot_command_line, arcs_cmdline, COMMAND_LINE_SIZE);
+#endif
+#else
+	strlcpy(boot_command_line, arcs_cmdline, COMMAND_LINE_SIZE);
+#endif
+	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
 
 	*cmdline_p = command_line;
 
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index 6254041b942f..d0c68b5d717b 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -35,6 +35,15 @@
 
 #include "signal-common.h"
 
+static int (*save_fp_context)(struct sigcontext __user *sc);
+static int (*restore_fp_context)(struct sigcontext __user *sc);
+
+extern asmlinkage int _save_fp_context(struct sigcontext __user *sc);
+extern asmlinkage int _restore_fp_context(struct sigcontext __user *sc);
+
+extern asmlinkage int fpu_emulator_save_context(struct sigcontext __user *sc);
+extern asmlinkage int fpu_emulator_restore_context(struct sigcontext __user *sc);
+
 /*
  * Horribly complicated - with the bloody RM9000 workarounds enabled
  * the signal trampolines is moving to the end of the structure so we can
@@ -709,3 +718,40 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused,
 			key_replace_session_keyring();
 	}
 }
+
+#ifdef CONFIG_SMP
+static int smp_save_fp_context(struct sigcontext __user *sc)
+{
+	return raw_cpu_has_fpu
+	       ? _save_fp_context(sc)
+	       : fpu_emulator_save_context(sc);
+}
+
+static int smp_restore_fp_context(struct sigcontext __user *sc)
+{
+	return raw_cpu_has_fpu
+	       ? _restore_fp_context(sc)
+	       : fpu_emulator_restore_context(sc);
+}
+#endif
+
+static int signal_setup(void)
+{
+#ifdef CONFIG_SMP
+	/* For now just do the cpu_has_fpu check when the functions are invoked */
+	save_fp_context = smp_save_fp_context;
+	restore_fp_context = smp_restore_fp_context;
+#else
+	if (cpu_has_fpu) {
+		save_fp_context = _save_fp_context;
+		restore_fp_context = _restore_fp_context;
+	} else {
+		save_fp_context = fpu_emulator_save_context;
+		restore_fp_context = fpu_emulator_restore_context;
+	}
+#endif
+
+	return 0;
+}
+
+arch_initcall(signal_setup);
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index 2e74075ac0ca..03abaf048f09 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -35,6 +35,15 @@
 
 #include "signal-common.h"
 
+static int (*save_fp_context32)(struct sigcontext32 __user *sc);
+static int (*restore_fp_context32)(struct sigcontext32 __user *sc);
+
+extern asmlinkage int _save_fp_context32(struct sigcontext32 __user *sc);
+extern asmlinkage int _restore_fp_context32(struct sigcontext32 __user *sc);
+
+extern asmlinkage int fpu_emulator_save_context32(struct sigcontext32 __user *sc);
+extern asmlinkage int fpu_emulator_restore_context32(struct sigcontext32 __user *sc);
+
 /*
  * Including <asm/unistd.h> would give use the 64-bit syscall numbers ...
  */
@@ -828,3 +837,18 @@ SYSCALL_DEFINE5(32_waitid, int, which, compat_pid_t, pid,
 	info.si_code |= __SI_CHLD;
 	return copy_siginfo_to_user32(uinfo, &info);
 }
+
+static int signal32_init(void)
+{
+	if (cpu_has_fpu) {
+		save_fp_context32 = _save_fp_context32;
+		restore_fp_context32 = _restore_fp_context32;
+	} else {
+		save_fp_context32 = fpu_emulator_save_context32;
+		restore_fp_context32 = fpu_emulator_restore_context32;
+	}
+
+	return 0;
+}
+
+arch_initcall(signal32_init);
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index e72e6844d134..6cdca1956b77 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -32,6 +32,7 @@
 #include <linux/cpumask.h>
 #include <linux/cpu.h>
 #include <linux/err.h>
+#include <linux/ftrace.h>
 
 #include <asm/atomic.h>
 #include <asm/cpu.h>
@@ -130,7 +131,7 @@ asmlinkage __cpuinit void start_secondary(void)
 /*
  * Call into both interrupt handlers, as we share the IPI for them
  */
-void smp_call_function_interrupt(void)
+void __irq_entry smp_call_function_interrupt(void)
 {
 	irq_enter();
 	generic_smp_call_function_single_interrupt();
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index a38e3ee95515..23499b5bd9c3 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -25,6 +25,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
 #include <linux/module.h>
+#include <linux/ftrace.h>
 
 #include <asm/cpu.h>
 #include <asm/processor.h>
@@ -939,23 +940,29 @@ static void ipi_call_interrupt(void)
 
 DECLARE_PER_CPU(struct clock_event_device, mips_clockevent_device);
 
-void ipi_decode(struct smtc_ipi *pipi)
+static void __irq_entry smtc_clock_tick_interrupt(void)
 {
 	unsigned int cpu = smp_processor_id();
 	struct clock_event_device *cd;
+	int irq = MIPS_CPU_IRQ_BASE + 1;
+
+	irq_enter();
+	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
+	cd = &per_cpu(mips_clockevent_device, cpu);
+	cd->event_handler(cd);
+	irq_exit();
+}
+
+void ipi_decode(struct smtc_ipi *pipi)
+{
 	void *arg_copy = pipi->arg;
 	int type_copy = pipi->type;
-	int irq = MIPS_CPU_IRQ_BASE + 1;
 
 	smtc_ipi_nq(&freeIPIq, pipi);
 
 	switch (type_copy) {
 	case SMTC_CLOCK_TICK:
-		irq_enter();
-		kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
-		cd = &per_cpu(mips_clockevent_device, cpu);
-		cd->event_handler(cd);
-		irq_exit();
+		smtc_clock_tick_interrupt();
 		break;
 
 	case LINUX_SMP_IPI:
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 0a18b4c62afb..308e43460864 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -25,10 +25,12 @@
 #include <linux/ptrace.h>
 #include <linux/kgdb.h>
 #include <linux/kdebug.h>
+#include <linux/notifier.h>
 
 #include <asm/bootinfo.h>
 #include <asm/branch.h>
 #include <asm/break.h>
+#include <asm/cop2.h>
 #include <asm/cpu.h>
 #include <asm/dsp.h>
 #include <asm/fpu.h>
@@ -79,10 +81,6 @@ extern asmlinkage void handle_reserved(void);
 extern int fpu_emulator_cop1Handler(struct pt_regs *xcp,
 	struct mips_fpu_struct *ctx, int has_fpu);
 
-#ifdef CONFIG_CPU_CAVIUM_OCTEON
-extern asmlinkage void octeon_cop2_restore(struct octeon_cop2_state *task);
-#endif
-
 void (*board_be_init)(void);
 int (*board_be_handler)(struct pt_regs *regs, int is_fixup);
 void (*board_nmi_handler_setup)(void);
@@ -857,6 +855,44 @@ static void mt_ase_fp_affinity(void)
 #endif /* CONFIG_MIPS_MT_FPAFF */
 }
 
+/*
+ * No lock; only written during early bootup by CPU 0.
+ */
+static RAW_NOTIFIER_HEAD(cu2_chain);
+
+int __ref register_cu2_notifier(struct notifier_block *nb)
+{
+	return raw_notifier_chain_register(&cu2_chain, nb);
+}
+
+int cu2_notifier_call_chain(unsigned long val, void *v)
+{
+	return raw_notifier_call_chain(&cu2_chain, val, v);
+}
+
+static int default_cu2_call(struct notifier_block *nfb, unsigned long action,
+        void *data)
+{
+	struct pt_regs *regs = data;
+
+	switch (action) {
+	default:
+		die_if_kernel("Unhandled kernel unaligned access or invalid "
+			      "instruction", regs);
+		/* Fall through  */
+
+	case CU2_EXCEPTION:
+		force_sig(SIGILL, current);
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block default_cu2_notifier = {
+	.notifier_call	= default_cu2_call,
+	.priority	= 0x80000000,		/* Run last  */
+};
+
 asmlinkage void do_cpu(struct pt_regs *regs)
 {
 	unsigned int __user *epc;
@@ -920,17 +956,9 @@ asmlinkage void do_cpu(struct pt_regs *regs)
 		return;
 
 	case 2:
-#ifdef CONFIG_CPU_CAVIUM_OCTEON
-		prefetch(&current->thread.cp2);
-		local_irq_save(flags);
-		KSTK_STATUS(current) |= ST0_CU2;
-		status = read_c0_status();
-		write_c0_status(status | ST0_CU2);
-		octeon_cop2_restore(&(current->thread.cp2));
-		write_c0_status(status & ~ST0_CU2);
-		local_irq_restore(flags);
-		return;
-#endif
+		raw_notifier_call_chain(&cu2_chain, CU2_EXCEPTION, regs);
+		break;
+
 	case 3:
 		break;
 	}
@@ -1367,77 +1395,6 @@ void *set_vi_handler(int n, vi_handler_t addr)
 	return set_vi_srs_handler(n, addr, 0);
 }
 
-/*
- * This is used by native signal handling
- */
-asmlinkage int (*save_fp_context)(struct sigcontext __user *sc);
-asmlinkage int (*restore_fp_context)(struct sigcontext __user *sc);
-
-extern asmlinkage int _save_fp_context(struct sigcontext __user *sc);
-extern asmlinkage int _restore_fp_context(struct sigcontext __user *sc);
-
-extern asmlinkage int fpu_emulator_save_context(struct sigcontext __user *sc);
-extern asmlinkage int fpu_emulator_restore_context(struct sigcontext __user *sc);
-
-#ifdef CONFIG_SMP
-static int smp_save_fp_context(struct sigcontext __user *sc)
-{
-	return raw_cpu_has_fpu
-	       ? _save_fp_context(sc)
-	       : fpu_emulator_save_context(sc);
-}
-
-static int smp_restore_fp_context(struct sigcontext __user *sc)
-{
-	return raw_cpu_has_fpu
-	       ? _restore_fp_context(sc)
-	       : fpu_emulator_restore_context(sc);
-}
-#endif
-
-static inline void signal_init(void)
-{
-#ifdef CONFIG_SMP
-	/* For now just do the cpu_has_fpu check when the functions are invoked */
-	save_fp_context = smp_save_fp_context;
-	restore_fp_context = smp_restore_fp_context;
-#else
-	if (cpu_has_fpu) {
-		save_fp_context = _save_fp_context;
-		restore_fp_context = _restore_fp_context;
-	} else {
-		save_fp_context = fpu_emulator_save_context;
-		restore_fp_context = fpu_emulator_restore_context;
-	}
-#endif
-}
-
-#ifdef CONFIG_MIPS32_COMPAT
-
-/*
- * This is used by 32-bit signal stuff on the 64-bit kernel
- */
-asmlinkage int (*save_fp_context32)(struct sigcontext32 __user *sc);
-asmlinkage int (*restore_fp_context32)(struct sigcontext32 __user *sc);
-
-extern asmlinkage int _save_fp_context32(struct sigcontext32 __user *sc);
-extern asmlinkage int _restore_fp_context32(struct sigcontext32 __user *sc);
-
-extern asmlinkage int fpu_emulator_save_context32(struct sigcontext32 __user *sc);
-extern asmlinkage int fpu_emulator_restore_context32(struct sigcontext32 __user *sc);
-
-static inline void signal32_init(void)
-{
-	if (cpu_has_fpu) {
-		save_fp_context32 = _save_fp_context32;
-		restore_fp_context32 = _restore_fp_context32;
-	} else {
-		save_fp_context32 = fpu_emulator_save_context32;
-		restore_fp_context32 = fpu_emulator_restore_context32;
-	}
-}
-#endif
-
 extern void cpu_cache_init(void);
 extern void tlb_init(void);
 extern void flush_tlb_handlers(void);
@@ -1751,13 +1708,10 @@ void __init trap_init(void)
 	else
 		memcpy((void *)(ebase + 0x080), &except_vec3_generic, 0x80);
 
-	signal_init();
-#ifdef CONFIG_MIPS32_COMPAT
-	signal32_init();
-#endif
-
 	local_flush_icache_range(ebase, ebase + 0x400);
 	flush_tlb_handlers();
 
 	sort_extable(__start___dbe_table, __stop___dbe_table);
+
+	register_cu2_notifier(&default_cu2_notifier);
 }
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index 67bd626942ab..69b039ca8d83 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -81,6 +81,7 @@
 #include <asm/asm.h>
 #include <asm/branch.h>
 #include <asm/byteorder.h>
+#include <asm/cop2.h>
 #include <asm/inst.h>
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -451,17 +452,27 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 		 */
 		goto sigbus;
 
+	/*
+	 * COP2 is available to implementor for application specific use.
+	 * It's up to applications to register a notifier chain and do
+	 * whatever they have to do, including possible sending of signals.
+	 */
 	case lwc2_op:
+		cu2_notifier_call_chain(CU2_LWC2_OP, regs);
+		break;
+
 	case ldc2_op:
+		cu2_notifier_call_chain(CU2_LDC2_OP, regs);
+		break;
+
 	case swc2_op:
+		cu2_notifier_call_chain(CU2_SWC2_OP, regs);
+		break;
+
 	case sdc2_op:
-		/*
-		 * These are the coprocessor 2 load/stores.  The current
-		 * implementations don't use cp2 and cp2 should always be
-		 * disabled in c0_status.  So send SIGILL.
-                 * (No longer true: The Sony Praystation uses cp2 for
-                 * 3D matrix operations.  Dunno if that thingy has a MMU ...)
-		 */
+		cu2_notifier_call_chain(CU2_SDC2_OP, regs);
+		break;
+
 	default:
 		/*
 		 * Pheeee...  We encountered an yet unknown instruction or
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 162b29954baa..f25df73db923 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -46,6 +46,7 @@ SECTIONS
 		SCHED_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
+		IRQENTRY_TEXT
 		*(.text.*)
 		*(.fixup)
 		*(.gnu.warning)